Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2766 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.8055. Min Act: -0.0001
Data Index: 512669 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.6534. Min Act: -0.0001
Data Index: 290053 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.5794. Min Act: -0.0001
Data Index: 60162 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.5182. Min Act: -0.0001
Data Index: 490425 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.3576. Min Act: -0.0001
Data Index: 217628 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.5795. Min Act: -0.0001
Data Index: 1038245 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.2354. Min Act: -0.0001
Data Index: 32432 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.4875. Min Act: -0.0001
Data Index: 728772 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.5098. Min Act: -0.0001
Data Index: 35848 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.4739. Min Act: -0.0001
Data Index: 998886 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.4047. Min Act: -0.0001
Data Index: 1354145 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.3200. Min Act: -0.0001
Data Index: 181233 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.2605. Min Act: -0.0001
Data Index: 117621 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.4335. Min Act: -0.0001
Data Index: 1264732 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.2934. Min Act: -0.0001
Data Index: 842244 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.4413. Min Act: -0.0001
Data Index: 362425 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.3576. Min Act: -0.0001
Data Index: 369614 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.2969. Min Act: -0.0001
Data Index: 115647 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.3184. Min Act: -0.0001
Data Index: 842321 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8055. Min Range: -1.8055
Max Act: 1.2255. Min Act: -0.0001
Data Index: 786158 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19